List tables and columns (MySQL) or collections and fields (MongoDB) in a specific schema. Provide the database ID and schema name to receive a map of object names to their column/field lists.
List tables->columns (MySQL) or collections->fields (MongoDB) in one schema. Returns a map of object name to column/field list.
| Name | Required | Description | Default |
|---|---|---|---|
| dbId | Yes | Database server id from list_databases | |
| schemaName | Yes | Schema name from get_schemas |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It reveals engine-specific behavior (MySQL tables vs MongoDB collections) and the exact return shape (a map of object name to column/field list), which makes the tool predictable. It does not discuss errors or authentication, but the listing verb clearly conveys a read-only metadata operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences: the first states the core action and engine variants, and the second states the return format. There is no filler, redundancy with the schema, or unnecessary background information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple, the schema fully documents its two parameters, and the description explains the return format in the absence of an output schema. The dual-engine behavior is covered, making it complete enough for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both parameters are already fully documented in the input schema, including their provenance from list_databases and get_schemas. The description adds general context about the output being per-schema, but it does not add per-parameter semantics beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('List'), resource ('tables->columns' or 'collections->fields'), and scope ('in one schema'). It is immediately distinguishable from sibling tools: list_databases lists servers, get_schemas lists schemas, and run_query executes queries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description and parameter names imply the intended workflow: use list_databases to get dbId, get_schemas to get schemaName, then this tool to inspect schema structure. It provides clear context but does not explicitly state when not to use it or mention run_query as an alternative for actual data retrieval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.